Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3362 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.0472. Min Range: -1.0472
Max Act: 1.0472. Min Act: -0.0001
Data Index: 728368 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0472. Min Range: -1.0472
Max Act: 1.0263. Min Act: -0.0001
Data Index: 669027 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9379. Min Act: -0.0001
Data Index: 1649478 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9020. Min Act: -0.0001
Data Index: 762207 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8860. Min Act: -0.0001
Data Index: 1968260 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9068. Min Act: -0.0001
Data Index: 166382 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8477. Min Act: -0.0001
Data Index: 364485 (The Pile)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9259. Min Act: -0.0001
Data Index: 1703299 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9735. Min Act: -0.0001
Data Index: 11647 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9582. Min Act: -0.0001
Data Index: 393311 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9167. Min Act: -0.0001
Data Index: 221504 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8896. Min Act: -0.0001
Data Index: 1779119 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.9340. Min Act: -0.0001
Data Index: 870441 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8824. Min Act: -0.0001
Data Index: 757024 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8044. Min Act: -0.0001
Data Index: 813633 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8146. Min Act: -0.0001
Data Index: 354213 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.7669. Min Act: -0.0001
Data Index: 527366 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8134. Min Act: -0.0001
Data Index: 276098 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.8305. Min Act: -0.0001
Data Index: 362943 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0472. Min Range: -1.0472
Max Act: 0.7806. Min Act: -0.0001
Data Index: 185909 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19